Analysis and modeling of fundamental frequency contours of English utterances

Fujisaki, Hiroya; Ohno, Sumio

doi:10.21437/eurospeech.1995-243

Cited by 20 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From this point of view, analysis has been made of F0 contours of a number of utterances of each of the following languages: English [13], Estonian [14], German [15], Greek [16], Korean [17], Polish, and Spanish [18]. The six panels (a)∼(f) in Fig.…”

Section: Languages With Only Positive Local Commandsmentioning

confidence: 99%

Information, prosody, and modeling - with emphasis on tonal features of speech -

Fujisaki

2004

Speech Prosody 2004

View full text Add to dashboard Cite

Starting from the author's view on the process of information manifestation in the tonal features of speech, this paper emphasizes the importance of objective and quantitative modeling in the study of these features. It then describes a model for the process of fundamental frequency control of speech that has been originally proposed and established for Japanese, and explains the physiological and physical evidences on which the model is based. Application of the model for generation of F0 contours of languages other than Japanese is then described, indicating how the original model can be modified and extended to cover those features that are not found in Japanese. The underlying mechanisms responsible for production of these features are also discussed.

show abstract

Section: Languages With Only Positive Local Commandsmentioning

confidence: 99%

Information, prosody, and modeling - with emphasis on tonal features of speech -

Fujisaki

2004

Speech Prosody 2004

View full text Add to dashboard Cite

show abstract

“…For the weight relative to the length of the previous word, W lpw , the length of the word is considered plus the length of the eventual pause. This factor assumes a higher correlation with presence of CF, for values above 0.5 s. The weight used for this factor is given by equation (2).…”

Section: Cfs Not Linked With Orthographic Marksmentioning

confidence: 99%

“…F0 is the most perceptually relevant component in prosody. The Fujisaki model of F0 was been proven to be well adapted with very high naturalness to several languages [1] like Japanese, Korean, Spanish, Polish, Greek, Swedish, English [2], German [3], Basque [4] and now also Portuguese. The Fujisaki model [1] consists of the logarithmic addition of baseline fundamental frequency, phrase components and accent components.…”

Section: Introductionmentioning

confidence: 99%

Prediction of fujisaki model's phrase commands

Teixeira¹,

Freitas²,

Fujisaki³

2003

8th European Conference on Speech Communication and Technology (Eurospeech 2003)

Self Cite

View full text Add to dashboard Cite

This paper presents a model to predict the phrase commands of the Fujisaki Model for F0 contour for the Portuguese Language. Phrase commands location in text is governed by a set of weighted rules. The amplitude (Ap) and timing (T0) of the phrase commands are predicted in separate neural networks. The features for both neural networks are discussed. Finally a comparison between target and predicted values is presented.

show abstract

“…Many functions were tested (linear, power, transfer, decay, exponential) for the best approximation of the natural F 0 contour. In the system presented, an exponential function for the phrase component P c (t) [14,16,17] was adopted and a cosinusoidal function for accents and final boundary contours A c (t). The F 0 contour is thus defined by the following equation:…”

Section: The Synthesis Schemementioning

confidence: 99%

“…This approach maximally reduces the amount of input prosodic information by applying a set of rules directly to the text. The so-called quantitative model of analysis and interpretation of the F 0 contour was proposed by many authors [12,13,14], with a differing number and complexity of the functions which try to simulate natural F 0 contours. In this paper, a global approach to modeling the F 0 contour is defined, mainly based on the so-called superpositional approach [14], which regards an F 0 contour as consisting of two different types of components:…”

Section: Introductionmentioning

confidence: 99%

Modeling segment intonation for Slovene TTS system

Dobnikar¹

1996

4th International Conference on Spoken Language Processing (ICSLP 1996)

View full text Add to dashboard Cite

A scheme for modeling the F 0 contour for different types of intonation units for the Slovene language is presented. It is based on results of analyzing F 0 contours, using a quantitative model. Data from ten speakers was collected, resulting in a large corpora, mainly of declarative sentences. A way of generating the F 0 contour for given utterances was defined, using only the text of the utterance as input. Near-to-natural synthesized F 0 contour was obtained by rules which regard the F 0 contour as the sum of global and local components.

show abstract

Analysis and modeling of fundamental frequency contours of English utterances

Cited by 20 publications

References 0 publications

Information, prosody, and modeling - with emphasis on tonal features of speech -

Information, prosody, and modeling - with emphasis on tonal features of speech -

Prediction of fujisaki model's phrase commands

Modeling segment intonation for Slovene TTS system

Contact Info

Product

Resources

About